Retrieval of Chlorophyll Content from Leaf Reflectance Spectra Using Support Vector Machine

Abstract:

The chlorophyll content in crop leaf is an indicator of health situation and the crop yield. Hence, it is very important to retrieval of accurate chlorophyll content in paddy rice. This research selected Zhengyi town of Suzhou city as the study area, measurements were acquired during the summer of 2009, in a field campaign in which for 288 rice leaf samples, rice hyperspectral data was measured by ASD FieldSpec3 spectrometer, chlorophyll content was measured by using a SPAD-502 chlorophyll meter. And the parameters of support vector machine were optimized by genetic algorithm, then support vector machine and PROSPECT radiative transfer model were adopted to build estimation model, which used to retrieve the chlorophyll content of rice. The results indicate that: the coefficient of determination for the rice chlorophyll estimation model is 0.8825, and RMSE is 8.7491. Research of this paper provides some reference for quickly and accurately estimating the chlorophyll content in rice.

• Periodical: Applied Mechanics and Materials (Volumes 602-605)
• Pages: 2313-2316
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.602-605.2313
• Online since: August 2014
• Authors: Jie Lv*, Zhen Guo Yan
• Keywords: Chlorophyll Content, Genetic Algorithm (GA), Inversion, Rice, Support Vector Machine (SVM)

References

[1] G. Hmimina, E. Dufrêne, K. Soudani, Relationship between photochemical reflectance index and leaf ecophysiological and biochemical parameters under two different water statuses: towards a rapid and efficient correction method using real-time measurements, Plant, Cell & Environment. 37 (2014).

DOI: 10.1111/pce.12171

[2] M. Vohland, S. Mader, W. Dorigo, Applying different inversion techniques to retrieve stand variables of summer barley with PROSPECT + SAIL, International Journal of Applied Earth Observation and Geoinformation. 12 (2010) 71-80.

DOI: 10.1016/j.jag.2009.10.005

[3] R. Houborg, H. Soegaard, E. Boegh, Combining vegetation index and model inversion methods for the extraction of key vegetation biophysical parameters using Terra and Aqua MODIS reflectance data, Remote Sensing of Environment. 106 (2007) 39-58.

DOI: 10.1016/j.rse.2006.07.016

[4] G. Duveiller, M. Weiss, F. Baret, P. Defourny, Retrieving wheat Green Area Index during the growing season from optical time series measurements based on neural network radiative transfer inversion, Remote Sensing of Environment. 115 (2011).

DOI: 10.1016/j.rse.2010.11.016

[5] G. Camps-Valls, L. Gómez-Chova, J. Muñoz-Marí, J. Vila-Francés, J. Amorós-López, J. Calpe-Maravilla, Retrieval of oceanic chlorophyll concentration with relevance vector machines, Remote Sensing of Environment. 105 (2006) 23-33.

DOI: 10.1117/12.627656

[6] S. T. Wang, C. L. Wang, W. B. Du, L. L. Tong, Research on the SVM Classification of Active and Passive Remote Sensing Data Based on the Feature Per-Parcel, Applied Mechanics and Materials. 405 (2013) 3001-3006.

DOI: 10.4028/www.scientific.net/amm.405-408.3001

[7] U. Maulik, D. Chakraborty, Learning with transductive SVM for semisupervised pixel classification of remote sensing imagery, ISPRS Journal of Photogrammetry and Remote Sensing. 77 (2013) 66-78.

DOI: 10.1016/j.isprsjprs.2012.12.003

[8] Y. Li, Y. Zhang, L. Jiang, Modeling Chlorophyll Content of Korean Pine Needles with NIR and SVM, Procedia Environmental Sciences. 10 (2011) 222-227.

DOI: 10.1016/j.proenv.2011.09.038